© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27512
    Prev
    Next
    INDEX
    Explanations

    cell identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yers
    -0.08
    ylan
    -0.08
    -rated
    -0.08
    ieval
    -0.07
    .Sprintf
    -0.07
    evice
    -0.07
    новÑĢемен
    -0.07
     Fus
    -0.07
    fers
    -0.07
    æı´
    -0.07
    POSITIVE LOGITS
     containing
    0.09
     chứa
    0.08
    åĨħçļĦ
    0.08
    åĨħæľī
    0.08
     boundaries
    0.07
    åĨħ
    0.07
    åĨħè¿Ľè¡Į
    0.07
     ÑĢазмеÑĢом
    0.07
    beat
    0.07
    contains
    0.07
    Activations Density 0.002%

    No Known Activations